{"id":"https://openalex.org/W2921603281","doi":"https://doi.org/10.1109/icra.2019.8793750","title":"Simulating Emergent Properties of Human Driving Behavior Using Multi-Agent Reward Augmented Imitation Learning","display_name":"Simulating Emergent Properties of Human Driving Behavior Using Multi-Agent Reward Augmented Imitation Learning","publication_year":2019,"publication_date":"2019-05-01","ids":{"openalex":"https://openalex.org/W2921603281","doi":"https://doi.org/10.1109/icra.2019.8793750","mag":"2921603281"},"language":"en","primary_location":{"id":"doi:10.1109/icra.2019.8793750","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2019.8793750","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1903.05766","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5017330847","display_name":"Raunak Bhattacharyya","orcid":"https://orcid.org/0000-0001-9254-8417"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Raunak P. Bhattacharyya","raw_affiliation_strings":["the Department of Aeronautics and Astronautics at Stanford University, Stanford Intelligent Systems Laboratory, Stanford, CA, USA","the Department of Aeronautics and Astronautics at Stanford University, Stanford Intelligent Systems Laboratory, Stanford, CA, 94305, USA"],"affiliations":[{"raw_affiliation_string":"the Department of Aeronautics and Astronautics at Stanford University, Stanford Intelligent Systems Laboratory, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"the Department of Aeronautics and Astronautics at Stanford University, Stanford Intelligent Systems Laboratory, Stanford, CA, 94305, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109358690","display_name":"Derek J. Phillips","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Derek J. Phillips","raw_affiliation_strings":["the Department of Aeronautics and Astronautics at Stanford University, Stanford Intelligent Systems Laboratory, Stanford, CA, USA","the Department of Aeronautics and Astronautics at Stanford University, Stanford Intelligent Systems Laboratory, Stanford, CA, 94305, USA"],"affiliations":[{"raw_affiliation_string":"the Department of Aeronautics and Astronautics at Stanford University, Stanford Intelligent Systems Laboratory, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"the Department of Aeronautics and Astronautics at Stanford University, Stanford Intelligent Systems Laboratory, Stanford, CA, 94305, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040156274","display_name":"Changliu Liu","orcid":"https://orcid.org/0000-0002-3767-5517"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Changliu Liu","raw_affiliation_strings":["the Department of Aeronautics and Astronautics at Stanford University, Stanford Intelligent Systems Laboratory, Stanford, CA, USA","the Department of Aeronautics and Astronautics at Stanford University, Stanford Intelligent Systems Laboratory, Stanford, CA, 94305, USA"],"affiliations":[{"raw_affiliation_string":"the Department of Aeronautics and Astronautics at Stanford University, Stanford Intelligent Systems Laboratory, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"the Department of Aeronautics and Astronautics at Stanford University, Stanford Intelligent Systems Laboratory, Stanford, CA, 94305, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002351623","display_name":"Jayesh K. Gupta","orcid":"https://orcid.org/0000-0002-4742-9942"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jayesh K. Gupta","raw_affiliation_strings":["the Department of Aeronautics and Astronautics at Stanford University, Stanford Intelligent Systems Laboratory, Stanford, CA, USA","the Department of Aeronautics and Astronautics at Stanford University, Stanford Intelligent Systems Laboratory, Stanford, CA, 94305, USA"],"affiliations":[{"raw_affiliation_string":"the Department of Aeronautics and Astronautics at Stanford University, Stanford Intelligent Systems Laboratory, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"the Department of Aeronautics and Astronautics at Stanford University, Stanford Intelligent Systems Laboratory, Stanford, CA, 94305, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059066811","display_name":"Katherine Driggs-Campbell","orcid":"https://orcid.org/0000-0003-3760-9859"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Katherine Driggs-Campbell","raw_affiliation_strings":["Department of Electrical and Computer Engineering, the University of Illinois at Urbana-Champaign, Urbana, IL","Department of Electrical and Computer Engineering, the University of Illinois at Urbana-Champaign, Urbana, IL, 61801"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, the University of Illinois at Urbana-Champaign, Urbana, IL","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, the University of Illinois at Urbana-Champaign, Urbana, IL, 61801","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068326377","display_name":"Mykel J. Kochenderfer","orcid":"https://orcid.org/0000-0002-7238-9663"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mykel J. Kochenderfer","raw_affiliation_strings":["the Department of Aeronautics and Astronautics at Stanford University, Stanford Intelligent Systems Laboratory, Stanford, CA, USA","the Department of Aeronautics and Astronautics at Stanford University, Stanford Intelligent Systems Laboratory, Stanford, CA, 94305, USA"],"affiliations":[{"raw_affiliation_string":"the Department of Aeronautics and Astronautics at Stanford University, Stanford Intelligent Systems Laboratory, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"the Department of Aeronautics and Astronautics at Stanford University, Stanford Intelligent Systems Laboratory, Stanford, CA, 94305, USA","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5017330847"],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":0.3819,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.64240258,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"789","last_page":"795"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10524","display_name":"Traffic control and management","score":0.9929999709129333,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.9182270765304565},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6744729280471802},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5657088160514832},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5608580112457275},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5430606603622437},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38599830865859985},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.17026278376579285},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.06485041975975037}],"concepts":[{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.9182270765304565},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6744729280471802},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5657088160514832},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5608580112457275},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5430606603622437},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38599830865859985},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.17026278376579285},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.06485041975975037},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icra.2019.8793750","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2019.8793750","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1903.05766","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1903.05766","pdf_url":"https://arxiv.org/pdf/1903.05766","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:2921603281","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1903.05766.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1903.05766","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1903.05766","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1903.05766","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1903.05766","pdf_url":"https://arxiv.org/pdf/1903.05766","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320315934","display_name":"Toyota Research Institute","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2921603281.pdf","grobid_xml":"https://content.openalex.org/works/W2921603281.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W158183001","https://openalex.org/W1542941925","https://openalex.org/W1771410628","https://openalex.org/W1777239053","https://openalex.org/W1965455100","https://openalex.org/W1986014385","https://openalex.org/W2099471712","https://openalex.org/W2168359464","https://openalex.org/W2294422333","https://openalex.org/W2328067583","https://openalex.org/W2545546008","https://openalex.org/W2580495915","https://openalex.org/W2604382266","https://openalex.org/W2737118859","https://openalex.org/W2739748921","https://openalex.org/W2768629321","https://openalex.org/W2787636963","https://openalex.org/W2883057932","https://openalex.org/W2949608212","https://openalex.org/W2951728940","https://openalex.org/W2963219401","https://openalex.org/W2963277051","https://openalex.org/W2963328631","https://openalex.org/W3148740559","https://openalex.org/W6606436731","https://openalex.org/W6638018090","https://openalex.org/W6638088447","https://openalex.org/W6638944445","https://openalex.org/W6696972564","https://openalex.org/W6718092244","https://openalex.org/W6741089554","https://openalex.org/W6741832134","https://openalex.org/W6746462176","https://openalex.org/W6748018442","https://openalex.org/W6753207554"],"related_works":["https://openalex.org/W3127247794","https://openalex.org/W201150177","https://openalex.org/W1987540542","https://openalex.org/W3093887912","https://openalex.org/W2144919070","https://openalex.org/W136420054","https://openalex.org/W1986869690","https://openalex.org/W3022312285","https://openalex.org/W2097113539","https://openalex.org/W2959614674","https://openalex.org/W1453801241","https://openalex.org/W3167475844","https://openalex.org/W3104485462","https://openalex.org/W2997479185","https://openalex.org/W2729615412","https://openalex.org/W2921549305","https://openalex.org/W2160485254","https://openalex.org/W2698595662","https://openalex.org/W2726187156","https://openalex.org/W2883343497"],"abstract_inverted_index":{"Recent":[0],"developments":[1],"in":[2,29,49,78,104,128,136,152],"multi-agent":[3,66,154],"imitation":[4,50,67,89,132],"learning":[5,68,90,133],"have":[6],"shown":[7],"promising":[8],"results":[9],"for":[10,48,87],"modeling":[11],"the":[12,37,65,72,88,95,139,147],"behavior":[13,148],"of":[14,97,138,142,149],"human":[15],"drivers.":[16],"However,":[17],"it":[18],"is":[19,102,113],"challenging":[20],"to":[21,36,74,130],"capture":[22],"emergent":[23,150],"traffic":[24,111],"behaviors":[25,33],"that":[26,43,84],"are":[27,44,92],"observed":[28],"real-world":[30],"datasets.":[31],"Such":[32],"arise":[34],"due":[35],"many":[38],"local":[39,140],"interactions":[40],"between":[41],"agents":[42],"not":[45],"commonly":[46],"accounted":[47],"learning.":[51],"This":[52,100],"paper":[53],"proposes":[54],"Reward":[55],"Augmented":[56],"Imitation":[57],"Learning":[58],"(RAIL),":[59],"which":[60],"integrates":[61],"reward":[62,98],"augmentation":[63],"into":[64],"framework":[69],"and":[70,146],"allows":[71],"designer":[73],"specify":[75],"prior":[76],"knowledge":[77],"a":[79,105,143],"principled":[80],"fashion.":[81],"We":[82],"prove":[83],"convergence":[85],"guarantees":[86],"process":[91],"preserved":[93],"under":[94],"application":[96],"augmentation.":[99],"method":[101],"validated":[103],"driving":[106,116],"scenario,":[107],"where":[108],"an":[109],"entire":[110],"scene":[112],"controlled":[114],"by":[115],"policies":[117],"learned":[118],"using":[119],"our":[120],"proposed":[121],"algorithm.":[122],"Further,":[123],"we":[124],"demonstrate":[125],"improved":[126],"performance":[127],"comparison":[129],"traditional":[131],"algorithms":[134],"both":[135],"terms":[137],"actions":[141],"single":[144],"agent":[145],"properties":[151],"complex,":[153],"settings.":[155]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}